paper-with-me

Papers

Recognizing Manipulation Actions from State-Transformations

2019-06-12 · Nachwa Aboubakr, James L. Crowley, Remi Ronfard

Manipulation actions transform objects from an initial state into a final state. In this paper, we report on the use of object state transitions as a mean for recognizing manipulation actions. Our method is inspired by the intuition that object states are visually more apparent than actions from a still frame and thus provide information that is complementary to spatio-temporal action recognition. We start by defining a state transition matrix that maps action labels into a pre-state and a post-state. From each keyframe, we learn appearance models of objects and their states. Manipulation actions can then be recognized from the state transition matrix. We report results on the EPIC kitchen action recognition challenge.

📄 PDF Abstract BibTeX arXiv:1906.05147

Code (1)

Nachwa/object_states 공식 구현 pytorch

Tasks

Action RecognitionObjectSpatio-temporal Action Recognition

Similar Papers 제목 키워드 기반

Problem Space Transformations for Out-of-Distribution Generalisation in Behavioural Cloning

2024-11-06 · Kiran Doshi, Marco Bagatella, Stelian Coros

The combination of behavioural cloning and neural networks has driven significant progress in robotic manipulation. As these algorithms may require a large number of demonstrations for each task of interest, they remain …

Behavioural cloning

Global Symmetry and Orthogonal Transformations from Geometrical Moment $n$-tuples

2026-02-08 · Omar Tahri arxiv

Detecting symmetry is crucial for effective object grasping for several reasons. Recognizing symmetrical features or axes within an object helps in developing efficient grasp strategies, as grasping along these axes typi…

Planning from Point Clouds over Continuous Actions for Multi-object Rearrangement

2025-09-04 · Kallol Saha, Amber Li, Angela Rodriguez-Izquierdo, Lifan Yu 외 arxiv

Long-horizon planning for robot manipulation is a challenging problem that requires reasoning about the effects of a sequence of actions on a physical 3D scene. While traditional task planning methods are shown to be eff…

Object RearrangementRobot ManipulationPoint Clouds

Understanding hand-object manipulation by modeling the contextual relationship between actions, grasp types and object attributes

2018-07-22 · Minjie Cai, Kris Kitani, Yoichi Sato

This paper proposes a novel method for understanding daily hand-object manipulation by developing computer vision-based techniques. Specifically, we focus on recognizing hand grasp types, object attributes and manipulati…

Object

Geometry-Aware Motion Latents for Learning Robust Manipulation Policies

2026-07-06 · Yunchao Zhang, Yijia Weng, Ruizhe Liu, Ming Hu 외 arxiv

Learning motion latents for robotic manipulation heavily relies on extracting motion patterns from visual sequences, yet effective action abstractions require understanding three-dimensional geometric transformations. He…

Point Clouds